interscript-maps 2.2.1 → 2.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7770cf9ef9d575be661e1ab0f7890d757e28dbb31493f88ea09fcccb05efbaa1
-  data.tar.gz: 4c9e662f53f5d77a27666823c4d8aec0c050fdbb6dada2ec77df78cb5a275998
+  metadata.gz: 73ee7bd0f92302a8534da56409afcea9e0c08f1645b9f40b7a100b02448c1ae6
+  data.tar.gz: 789d6049ad59dc694d2d4051339e3500be11b9d1af9327b130c96d29f3d8b625
 SHA512:
-  metadata.gz: 02d5302ba2245cc7197fb6e4025436f3337c210e7211c20dd5553ae7757f495c31e6a1f1b746c71c4dc6e8d0913b9d6c1686f5345c850423ec4abade560cf1e3
-  data.tar.gz: 0b0087d68fd3f363ecec221ce3edf1a1e5f99a14088bee500553250eccb0a48a059a97475903d765b1ec7c8d875fdbb21db4002d10d9e351e8e31f88e687bcf7
+  metadata.gz: ff801e6bf560173c2ec9be62bb548afc14c46f9402c66443fd93ba1c1e63637c8d1afccf82acf0c9d22912a65d5e3b872a091de9d574b87f925bb3da8362dfd1
+  data.tar.gz: 71dcaa6597cca6848d370a216e40b301e91105d15895c90bc29332a2ce5f6090c56e04164e17083be79f143645b836f0342537e482af2e61af733db9f119c0fd

data/interscript-maps.gemspec

@@ -1,4 +1,4 @@
-INTERSCRIPT_MAPS_VERSION="2.2.1"
+INTERSCRIPT_MAPS_VERSION="2.3.0"
 
 Gem::Specification.new do |spec|
   spec.name          = "interscript-maps"

data/interscript-maps.yaml

@@ -16,6 +16,32 @@ staging:
 secryst-models:
   - https://raw.githubusercontent.com/secryst/data-thai-interscript/master/index.yaml
 
+# Here we describe Rababa configs for the maps that are required
+rababa-configs:
+  "200":
+    model: https://github.com/secryst/rababa-models/releases/download/0.1/diacritization_model_max_len_200.onnx
+    config:
+      session_name: base
+      text_encoder: ArabicEncoderWithStartSymbol
+      text_cleaner: valid_arabic_cleaners
+      max_len: 200
+      batch_size: 32
+      
+# This instruction denotes that the following maps are incompatible with certain
+# compilers and platforms and shouldn't be tested or compiled in.
+skip:
+  Interscript::Compiler::Javascript:
+    - var-ara-Arab-Arab-rababa
+  # Windows currently fails tests for rababa
+  mswin64:
+    - var-ara-Arab-Arab-rababa
+  mswin32:
+    - var-ara-Arab-Arab-rababa
+  mingw32:
+    - var-ara-Arab-Arab-rababa
+  cygwin:
+    - var-ara-Arab-Arab-rababa
+
 # This part registers aliases. Those were previously a part of maps themselves,
 # moving this here saves us from a burden of having to load all the maps to
 # locate one that we are trying to access.

data/maps/alalc-mal-Mlym-Latn-2012.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mal
   source_script: Mlym
   destination_script: Latn
-  name: Malayalam Romanization, 2012
+  name: Romanization Table -- Malayalam (2012)
   url: https://www.loc.gov/catdir/cpso/romanization/malayalam.pdf
   creation_date: 2012
   description: |

data/maps/bas-rus-Cyrl-Latn-2017-bss.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:rus
   source_script: Cyrl
   destination_script: Latn
-  name: Streamlined Romanization of Russian Cyrillic -- Basic Streamlined System
+  name: Streamlined Romanization of Russian Cyrillic (Basic Streamlined System)
   url: https://www.researchgate.net/publication/318402098
   creation_date: 2017-07
   description: |

data/maps/bas-rus-Cyrl-Latn-2017-oss.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:rus
   source_script: Cyrl
   destination_script: Latn
-  name: Streamlined Romanization of Russian Cyrillic -- Optimized Streamlined System
+  name: Streamlined Romanization of Russian Cyrillic (Optimized Streamlined System)
   url: https://www.researchgate.net/publication/318402098
   creation_date: 2017-07
   description: |

data/maps/bgn-jpn-Hrkt-Latn-1962.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:jpn
   source_script: Hrkt
   destination_script: Latn
-  name: BGN Modified Hepburn Japanese transliteration system (1962)
+  name: Japanese Modified Hepburn (1962)
   url:
   creation_date: 1930
   adoption_date: 1962

data/maps/bgn-kor-Hang-Latn-1943.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: BGN Agreement -- Korean McCune-Reischauer System (Hangul to Latin) (1943)
+  name: Korean McCune-Reischauer (Hangul to Latin) (1943 Agreement)
   url:
   creation_date: 1943
   adoption_date:

data/maps/bgn-kor-Kore-Latn-1943.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kor
   source_script: Kore
   destination_script: Latn
-  name: BGN Agreement -- Korean McCune-Reischauer System (Korean to Latin) (1943)
+  name: Korean McCune-Reischauer (Korean to Latin) (1943 Agreement)
   url:
   creation_date: 1943
   adoption_date:

data/maps/bgnpcgn-bak-Cyrl-Latn-2007.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:rus
   source_script: Cyrl
   destination_script: Latn
-  name: BASHKIR TABLE OF CORRESPONDENCES CYRILLIC-ROMAN BGN/PCGN 2007 Agreement
+  name: Table of Correspondences for Bashkir (Cyrillic-Roman) (2007 Agreement)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/829203/TABLE_OF_CORRESPONDENCES__FOR_BASHKIR.pdf
   creation_date: 2007
   confirmation_date: 2019

data/maps/bgnpcgn-bel-Cyrl-Latn-1979.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:bel
   source_script: Cyrl
   destination_script: Latn
-  name: United States Board on Geographic Names Foreign Names Committee Staff, 1994. Romanization Systems and Roman-Script Spelling Conventions, p. 23.
+  name: Romanization of Belarusian (1979)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811510/ROMANIZATION_OF_BELARUSIAN.pdf
   creation_date: 1979
   description: |
@@ -12,6 +12,9 @@ metadata {
     romanizing names written in the Belarusian Cyrillic alphabet. The Belarusian alphabet contains three
     characters not present in the Russian alphabet: і, ў, and ’.
 
+    United States Board on Geographic Names Foreign Names Committee Staff, 1994.
+    Romanization Systems and Roman-Script Spelling Conventions, p. 23.
+
   notes:
    - The character sequences зг, кг, сг, тс and цг and may be romanized z·h, k·h, s·h, t·s and ts·h in order to differentiate those romanizations from the digraphs zh, kh, sh, ts, and the letter sequence tsh, which are used to render the characters ж, x, ш, ц, and the character sequence тш
    - All apostrophes appearing in romanization are Unicode encoding 2019.

data/maps/bgnpcgn-che-Cyrl-Latn-2008.imp

@@ -4,7 +4,8 @@ metadata {
   language: iso-639-2:che
   source_script: Cyrl
   destination_script: Latn
-  name: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/835782/TABLE_OF_CORRESPONDENCES_FOR_CHECHEN.pdf
+  name: Table of Correspondences for Chechen (Cyrillic-Roman) (2008 Agreement)
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/835782/TABLE_OF_CORRESPONDENCES_FOR_CHECHEN.pdf
   creation_date: 2008
   confirmation_date: 2019-07
   description: |

data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: Romanization of Korean -- For DPRK (Hangul to Latin) (1945 Agreement)
+  name: Romanization of Korean for DPRK (Hangul-Latin) (1945 Agreement)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693725/ROMANIZATION_OF_KOREAN-_MR_for_DPRK.pdf
   creation_date: 1945
   adoption_date:

data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.imp

@@ -4,14 +4,14 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: Romanization of Korean -- For the ROK (2011 Agreement, Ministry of Culture and Tourism System (2000))
+  name: Romanization of Korean for ROK (Hangul-Latin) (2011 Agreement, MOCT System 2000)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693724/ROMANIZATION_OF_KOREAN-__MOCT_for_ROK.pdf
   creation_date: 2011
   adoption_date: 2011
   description:
 
   notes:
-    BGN/PCGN 2011 Agreement
+  - BGN/PCGN 2011 Agreement
 }
 
 tests {

data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.imp

@@ -4,9 +4,8 @@ metadata {
   language: iso-639-2:kor
   source_script: Kore
   destination_script: Latn
-  name: Romanization of Korean -- For the ROK -- Korean to Latin (2011 Agreement, Ministry of Culture and Tourism System (2000))
+  name: Romanization of Korean for ROK (Korean-Latin) (2011 Agreement, MOCT System 2000)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693724/ROMANIZATION_OF_KOREAN-__MOCT_for_ROK.pdf
-  url: ""
   creation_date: 2011
   adoption_date: 2011
   description: |
@@ -14,7 +13,7 @@ metadata {
     Intended to provide a means for international communication of written documents.
 
   notes:
-    - BGN/PCGN 2011 Agreement
+  - BGN/PCGN 2011 Agreement
 }
 
 tests {

data/maps/bis-asm-Beng-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:asm
   source_script: Beng
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Assamese Romanization
+  name: Indian script code for information interchange (ISCII) -- Assamese Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-ben-Beng-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ben
   source_script: Beng
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Bengali Romanization
+  name: Indian script code for information interchange (ISCII) -- Bengali Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-dev-Deva-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:dev
   source_script: Deva
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Devanagri Romanization
+  name: Indian script code for information interchange (ISCII) -- Devanagri Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-guj-Gujr-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:guj
   source_script: Gujr
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Gujrati Romanization
+  name: Indian script code for information interchange (ISCII) -- Gujrati Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-kan-Kana-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kan
   source_script: Kana
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Kannada Romanization
+  name: Indian script code for information interchange (ISCII) -- Kannada Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-mlm-Mlym-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mlm
   source_script: Mlym
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Malayalam Romanization
+  name: Indian script code for information interchange (ISCII) -- Malayalam Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-ori-Orya-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ori
   source_script: Orya
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Oriya Romanization
+  name: Indian script code for information interchange (ISCII) -- Oriya Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-pnj-Guru-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:pnj
   source_script: Guru
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Panjabi(Gurmukhi) Romanization
+  name: Indian script code for information interchange (ISCII) -- Panjabi(Gurmukhi) Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-tel-Telu-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tel
   source_script: Telu
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Telegu Romanization
+  name: Indian script code for information interchange (ISCII) -- Telegu Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-tml-Taml-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tml
   source_script: Taml
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Tamil Romanization
+  name: Indian script code for information interchange (ISCII) -- Tamil Romanization
 
   #url:
   creation_date: 1991

data/maps/din-hin-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Hindi"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Hindi"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/din-kat-Geor-Latn-32707-2010.imp

@@ -9,8 +9,8 @@ metadata {
   creation_date: 2010
   confirmation_date: 2010
   description: |
-    Information and documentation - Romanization of the Georgian alphabet.
-  
+    Information and documentation -- Romanization of the Georgian alphabet.
+
   notes:
 }
 
@@ -53,27 +53,27 @@ stage {
     sub "\u10d4", "e" # ე
     sub "\u10d5", "v" # ვ
     sub "\u10d6", "z" # ზ
-    
+
     sub "\u10f1", "ê" # ჱ
-    
+
     sub "\u10d7", "t̕" # თ
     sub "\u10d8", "i" # ი
     sub "\u10d9", "k" # კ
     sub "\u10da", "l" # ლ
     sub "\u10db", "m" # მ
     sub "\u10dc", "n" # ნ
-    
+
     sub "\u10f2", "y" # ჲ
-    
+
     sub "\u10dd", "o" # ო
     sub "\u10de", "p" # პ
     sub "\u10df", "ž" # ჟ
     sub "\u10e0", "r" # რ
     sub "\u10e1", "s" # ს
     sub "\u10e2", "t" # ტ
-    
+
     sub "\u10f3", "w" # ჳ
-    
+
     sub "\u10e3", "u" # უ
     sub "\u10e4", "p̕" # ფ
     sub "\u10e5", "k̕" # ქ
@@ -86,14 +86,14 @@ stage {
     sub "\u10ec", "c" # წ
     sub "\u10ed", "č" # ჭ
     sub "\u10ee", "x" # ხ
-    
+
     sub "\u10f4", "q̕" # ჴ
-    
+
     sub "\u10ef", "ǰ" # ჯ
     sub "\u10f0", "h" # ჰ
-    
+
     sub "\u10f5", "ô" # ჵ
-    
+
     sub "\u10f6", "f" # ჶ
     sub "\u10f7", "ẹ" # ჷ
     sub "\u10f8", "ʼ" # ჸ

data/maps/din-mar-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mar
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Marathi"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Marathi"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/din-nep-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:nep
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Nepali"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Nepali"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/din-pli-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:pli
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Pali"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Pali"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/din-pra-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:pra
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Prakit"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Prakit"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/din-san-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:san
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Sanskrit"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Sanskrit"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/elot-ell-Grek-Latn-743-1982-tl.imp

@@ -4,12 +4,11 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: ELOT 743:1982 (transliteration)
+  name: ELOT 743:1982 Information and documentation -- Conversion of Greek characters into Latin characters (transliteration system)
   url:
   creation_date: 1982
   description: |
     ELOT 743:1982 transliteration table for Greek
-
   notes:
     - This was the intended system in ELOT 743:1982 for transliteration, as is apparent from un-ell-Grek-Latn-1987-tl and iso-ell-Grek-Latn-843-1997-t2, and ELOT 743:2001, Annex B; but the reversible character diacritics are missing from the currently available document, and the document does not indicate what there was supposed to be.
     - "\"Transliteration\" as used in this specification and its inheritors refers to reversible transliteration, as distinct from \"transcription\", which is a simpler transliteration and which is intended for default use."